Ruslan Salakhutdinov

Assistant Professor
Microsoft Faculty Fellow
Sloan Fellow
University of Toronto
CV Google Scholar  

I am an assistant professor of Computer Science and Statistics at the University of Toronto. I work in the field of statistical machine learning (See my CV.)

I received my PhD in computer science from the University of Toronto in 2009. After spending two post-doctoral years at MIT, I joined the University of Toronto in 2011.

My research interests include Deep Learning, Probabilistic Graphical Models, and Large-scale Optimization.

Prospective students: Please read this to ensure that I read your email.

Recent Research Highlights:

Recent Papers:

  • Unsupervised Learning of Video Representations using LSTMs
    Nitish Srivastava, Elman Mansimov, Ruslan Salakhutdinov
    [arXiv], 2015

  • Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
    Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhutdinov, Richard Zemel, Yoshua Bengio
    [arXiv], 2015

  • Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models
    Ryan Kiros, Ruslan Salakhutdinov, Richard Zemel.
    To appear in Transactions of the Association for Computational Linguistics (TACL), 2015.
    [ arXiv], [ results], [ demo ].
    An encoder-decoder architecture for ranking and generating image descriptions.
    Previous version appeared in NIPS Deep Learning Workshop, 2014.

  • Accurate and Conservative Estimates of MRF Log-likelihood using Reverse Annealing
    Yuri Burda, Roger B. Grosse, and Ruslan Salakhutdinov,
    To appear in AI and Statistics, 2015 [arXiv]

  • Learning Generative Models with Visual Attention
    Yichuan Tang, Nitish Srivastava, and Ruslan Salakhutdinov
    Neural Information Processing Systems (NIPS 28), 2014, oral,
    [ pdf ], Supplementary material [ pdf].

  • A Multiplicative Model for Learning Distributed Text-Based Attribute Representations
    Ryan Kiros, Richard Zemel, Ruslan Salakhutdinov.
    Neural Information Processing Systems (NIPS 28), 2014.
    [ pdf ], Supplementary material [ zip].

  • Multimodal Learning with Deep Boltzmann Machines
    Nitish Srivastava and Ruslan Salakhutdinov
    Journal of Machine Learning Research, 2014. [ pdf ]. Code is available [ here].

  • Dropout: A simple way to prevent neural networks from overfitting
    Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan R. Salakhutdinov
    Journal of Machine Learning Research, 2014. [ pdf].

  • Deep Learning for Neuroimaging: a Validation Study
    S. Plis, D. Hjelm, R. Salakhutdinov, E. Allen, H. Bockholt, J. Long, H. Johnson, J. Paulsen, J. Turner, and V. Calhoun
    Frontiers in Neuroscience, 2014. [ pdf].

  • Multi-task Neural Networks for QSAR Prediction
    George E. Dahl, Navdeep Jaitly, Ruslan Salakhutdinov, 2014.
    [ arXiv].

  • Restricted Boltzmann Machines for Neuroimaging: An Application in Identifying Intrinsic Networks
    Devon Hjelma, Vince Calhouna, Ruslan Salakhutdinov, Elena Allena, Tulay Adali, and Sergey Plisa
    In NeuroImage, Volume 96, Aug 1 2014, pages 245 - 260. [ pdf].

  • Multimodal Neural Language Models
    Ryan Kiros, Ruslan Salakhutdinov, Richard Zemel.
    In 31th International Conference on Machine Learning (ICML 2014)
    [pdf], [ Project Page].